Magyar
Toggle navigation
Tudóstér
Magyar
Tudóstér
Keresés
Egyszerű keresés
Összetett keresés
CCL keresés
Egyszerű keresés
Összetett keresés
CCL keresés
Böngészés
Saját polc tartalma
(
0
)
Korábbi keresések
Összesen 1 találat.
#/oldal:
12
36
60
120
Rövid
Hosszú
MARC
Részletezés:
Rendezés:
Szerző növekvő
Szerző csökkenő
Cím növekvő
Cím csökkenő
Dátum növekvő
Dátum csökkenő
1.
001-es BibID:
BIBFORM124177
Első szerző:
Gandhi, Herry Kartika (industrial engineer)
Cím:
Mid-term forecasting of crude oil prices using hybrid CEEMDAN and CNN_LSTM deep learning model / Herry Kartika Gandhi
Dátum:
2024
Megjegyzések:
Forecasting crude oil prices has always been a matter of discussion among energy experts. Due to society's dependence on crude oil, the vulnerability of its price value can significantly negatively impact the world of economics and business. Moreover, crude oil is still the primary energy source worldwide, and although renewable energy sources have developed significantly, crude oil trade between countries as an energy source will remain dominant for the next few years. This study focuses on mid-term multi-step forecasting and provides a forecasting model that provides robust prediction for 60 to 90 steps ahead. Our main objective is to develop a forecasting model that can maintain stability to improve accuracy and reduce errors. Our analysis uses a hybrid Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Convolutional Neural Network, Long Short-Term Memory (CNN_LSTM) deep learning model. These three techniques, which have different advantages, are put together, and the combination of them is able to identify features in historical data learning and perform high prediction accuracy for the next term. We compared the proposed model with other decomposition and deep learning techniques. The proposed model shows lower MAE and RMSE values than other benchmark models for Brent and crude WTI oil prices the proposed model's MAPE results in better forecasting from 4 to 10. The simulation with box plot analysis also gives a quartile range value below 0.2, which shows the stability of the model in each iteration. Finally, the proposed model can provide a robust forecasting model for multi-step mid-term forecasting.
Tárgyszavak:
Műszaki tudományok
Informatikai tudományok
idegen nyelvű folyóiratközlemény külföldi lapban
folyóiratcikk
forecasting
crude oil price
CEEMDAN
convolutional neural network
long short-term memory
Megjelenés:
Polityka Energetyczna = Energy Policy Journal. - accepted for publication : - (2024), p. [1-36]. -
Internet cím:
Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:
Rekordok letöltése
1
Corvina könyvtári katalógus v8.2.27
© 2023
Monguz kft.
Minden jog fenntartva.